ICTS:32498

New research directions in vector search

(2025). New research directions in vector search. SciVideos. https://scivideos.org/icts-tifr/32498

New research directions in vector search. SciVideos, Aug. 12, 2025, https://scivideos.org/icts-tifr/32498 

          @misc{ scivideos_ICTS:32498,
            doi = {},
            url = {https://scivideos.org/icts-tifr/32498},
            author = {},
            keywords = {},
            language = {en},
            title = {New research directions in vector search},
            publisher = {},
            year = {2025},
            month = {aug},
            note = {ICTS:32498 see, \url{https://scivideos.org/icts-tifr/32498}}
          }
Kiran Shiragur
Talk numberICTS:32498
Source RepositoryICTS-TIFR

Abstract

Vector search is a fundamental problem with numerous applications in machine learning, computer vision, recommendation systems, and more. While vector search has been extensively studied, modern applications have introduced new requirements, such as diversity, multivector, multifilter, and others. In this talk, we explore these emerging research directions, with a focus on diversity and multivector embeddings in vector search.

For both problems, we propose the first provable graph-based algorithms that efficiently return approximate solutions. Our algorithms leverage popular graph-based methods, enabling us to build on existing, efficient implementations. Experimental results show that our algorithms outperform other approaches.